A fundamental problem in statistics and learning theory is to test properties of distributions. We show that quantum computers can solve such problems with significant speed-ups. In particular, we give fast quantum algorithms for testing closeness between unknown distributions, testing independence between two distributions, and estimating the Shannon / von Neumann entropy of distributions. The distributions can be either classical or quantum, however our quantum algorithms require coherent quantum access to a process preparing the samples. Our results build on the recent technique of quantum singular value transformation, combined with more standard tricks such as divide-and-conquer. The presented approach is a natural fit for distributional property testing both in the classical and the quantum case, demonstrating the first speed-ups for testing properties of density operators that can be accessed coherently rather than only via sampling; for classical distributions our algorithms significantly improve the precision dependence of some earlier results.

}, url = {https://arxiv.org/abs/1902.00814}, author = {Andras Gilyen and Tongyang Li} } @article {2338, title = {Quantum-inspired classical sublinear-time algorithm for solving low-rank semidefinite programming via sampling approaches}, year = {2019}, abstract = {Semidefinite programming (SDP) is a central topic in mathematical optimization with extensive studies on its efficient solvers. Recently, quantum algorithms with superpolynomial speedups for solving SDPs have been proposed assuming access to its constraint matrices in quantum superposition. Mutually inspired by both classical and quantum SDP solvers, in this paper we present a sublinear classical algorithm for solving low-rank SDPs which is asymptotically as good as existing quantum algorithms. Specifically, given an SDP with m constraint matrices, each of dimension n and rank poly(logn), our algorithm gives a succinct description and any entry of the solution matrix in time O(m\⋅poly(logn,1/ε)) given access to a sample-based low-overhead data structure of the constraint matrices, where ε is the precision of the solution. In addition, we apply our algorithm to a quantum state learning task as an application. Technically, our approach aligns with both the SDP solvers based on the matrix multiplicative weight (MMW) framework and the recent studies of quantum-inspired machine learning algorithms. The cost of solving SDPs by MMW mainly comes from the exponentiation of Hermitian matrices, and we propose two new technical ingredients (compared to previous sample-based algorithms) for this task that may be of independent interest: . Weighted sampling: assuming sampling access to each individual constraint matrix A1,\…,Aτ, we propose a procedure that gives a good approximation of A=A1+...+Aτ. . Symmetric approximation: we propose a sampling procedure that gives low-rank spectral decomposition of a Hermitian matrix A. This improves upon previous sampling procedures that only give low-rank singular value decompositions, losing the signs of eigenvalues.

}, url = {https://arxiv.org/abs/1901.03254}, author = {Nai-Hui Chia and Tongyang Li and Han-Hsuan Lin and Chunhao Wang} } @article {2376, title = {Sublinear quantum algorithms for training linear and kernel-based classifiers}, year = {2019}, month = {04/03/2019}, abstract = {We investigate quantum algorithms for classification, a fundamental problem in machine learning, with provable guarantees. Given n d-dimensional data points, the state-of-the-art (and optimal) classical algorithm for training classifiers with constant margin runs in O~(n+d) time. We design sublinear quantum algorithms for the same task running in O~(n\−\−\√+d\−\−\√) time, a quadratic improvement in both n and d. Moreover, our algorithms use the standard quantization of the classical input and generate the same classical output, suggesting minimal overheads when used as subroutines for end-to-end applications. We also demonstrate a tight lower bound (up to poly-log factors) and discuss the possibility of implementation on near-term quantum machines. As a side result, we also give sublinear quantum algorithms for approximating the equilibria of n-dimensional matrix zero-sum games with optimal complexity Θ~(n\−\−\√).\

}, url = {https://arxiv.org/abs/1904.02276}, author = {Tongyang Li and Shouvanik Chakrabarti and Xiaodi Wu} } @article {2207, title = {Quantum algorithms and lower bounds for convex optimization}, year = {2018}, abstract = {While recent work suggests that quantum computers can speed up the solution of semidefinite programs, little is known about the quantum complexity of more general convex optimization. We present a quantum algorithm that can optimize a convex function over an n-dimensional convex body using O~(n) queries to oracles that evaluate the objective function and determine membership in the convex body. This represents a quadratic improvement over the best-known classical algorithm. We also study limitations on the power of quantum computers for general convex optimization, showing that it requires Ω~(n\−\−\√) evaluation queries and Ω(n\−\−\√) membership queries.

}, url = {https://arxiv.org/abs/1809.01731}, author = {Shouvanik Chakrabarti and Andrew M. Childs and Tongyang Li and Xiaodi Wu} } @article {2309, title = {Quantum SDP Solvers: Large Speed-ups, Optimality, and Applications to Quantum Learning}, year = {2018}, abstract = {We give two new quantum algorithms for solving semidefinite programs (SDPs) providing quantum speed-ups. We consider SDP instances with m constraint matrices, each of dimension n, rank r, and sparsity s. The first algorithm assumes an input model where one is given access to entries of the matrices at unit cost. We show that it has run time O~(s2(m\−\−\√ε\−10+n\−\−\√ε\−12)), where ε is the error. This gives an optimal dependence in terms of m,n and quadratic improvement over previous quantum algorithms when m\≈n. The second algorithm assumes a fully quantum input model in which the matrices are given as quantum states. We show that its run time is O~(m\−\−\√+poly(r))\⋅poly(logm,logn,B,ε\−1), with B an upper bound on the trace-norm of all input matrices. In particular the complexity depends only poly-logarithmically in n and polynomially in r. We apply the second SDP solver to the problem of learning a good description of a quantum state with respect to a set of measurements: Given m measurements and copies of an unknown state ρ, we show we can find in time m\−\−\√\⋅poly(logm,logn,r,ε\−1) a description of the state as a quantum circuit preparing a density matrix which has the same expectation values as ρ on the m measurements, up to error ε. The density matrix obtained is an approximation to the maximum entropy state consistent with the measurement data considered in Jaynes\&$\#$39; principle from statistical mechanics. As in previous work, we obtain our algorithm by \"quantizing\" classical SDP solvers based on the matrix multiplicative weight method. One of our main technical contributions is a quantum Gibbs state sampler for low-rank Hamiltonians with a poly-logarithmic dependence on its dimension, which could be of independent interest.

}, url = {https://arxiv.org/abs/1710.02581}, author = {Fernando G. S. L. Brand{\~a}o and Amir Kalev and Tongyang Li and Cedric Yen-Yu Lin and Krysta M. Svore and Xiaodi Wu} } @article {1902, title = {Efficient simulation of sparse Markovian quantum dynamics}, journal = {Quantum Information and Computation}, volume = {17}, year = {2017}, month = {2017/09/01}, pages = {901-947}, abstract = {Quantum algorithms for simulating Hamiltonian dynamics have been extensively developed, but there has been much less work on quantum algorithms for simulating the dynamics of open quantum systems. We give the first efficient quantum algorithms for simulating Markovian quantum dynamics generated by Lindbladians that are not necessarily local. We introduce two approaches to simulating sparse Lindbladians. First, we show how to simulate Lindbladians that act within small invariant subspaces using a quantum algorithm to implement sparse Stinespring isometries. Second, we develop a method for simulating sparse Lindblad operators by concatenating a sequence of short-time evolutions. We also show limitations on Lindbladian simulation by proving a no-fast-forwarding theorem for simulating sparse Lindbladians in a black-box model.

}, doi = {10.26421/QIC17.11-12}, url = {https://arxiv.org/abs/1611.05543}, author = {Andrew M. Childs and Tongyang Li} } @article {2106, title = {Exponential Quantum Speed-ups for Semidefinite Programming with Applications to Quantum Learning}, year = {2017}, month = {2017/10/06}, abstract = {We give semidefinite program (SDP) quantum solvers with an exponential speed-up over classical ones. Specifically, we consider SDP instances with m constraint matrices of dimension n, each of rank at most r, and assume that the input matrices of the SDP are given as quantum states (after a suitable normalization). Then we show there is a quantum algorithm that solves the SDP feasibility problem with accuracy ǫ by using \√ m log m \· poly(log n,r, ǫ \−1 ) quantum gates. The dependence on n provides an exponential improvement over the work of Brand \˜ao and Svore [6] and the work of van Apeldoorn et al. [23], and demonstrates an exponential quantum speed-up when m and r are small. We apply the SDP solver to the problem of learning a good description of a quantum state with respect to a set of measurements: Given m measurements and a supply of copies of an unknown state ρ, we show we can find in time \√ m log m \· poly(log n,r, ǫ \−1 ) a description of the state as a quantum circuit preparing a density matrix which has the same expectation values as ρ on the m measurements up to error ǫ. The density matrix obtained is an approximation to the maximum entropy state consistent with the measurement data considered in Jaynes\’ principle. As in previous work, we obtain our algorithm by \“quantizing\” classical SDP solvers based on the matrix multiplicative weight update method. One of our main technical contributions is a quantum Gibbs state sampler for low-rank Hamiltonians with a poly-logarithmic dependence on its dimension based on the techniques developed in quantum principal component analysis, which could be of independent interest. Our quantum SDP solver is different from previous ones in the following two aspects: (1) it follows from a zero-sum game approach of Hazan [11] of solving SDPs rather than the primal-dual approach by Arora and Kale [5]; and (2) it does not rely on any sparsity assumption of the input matrices.

}, url = {https://arxiv.org/abs/1710.02581}, author = {Fernando G. S. L. Brand{\~a}o and Amir Kalev and Tongyang Li and Cedric Yen-Yu Lin and Krysta M. Svore and Xiaodi Wu} } @article {2105, title = {Quantum query complexity of entropy estimation}, year = {2017}, month = {2017/10/16}, abstract = {Estimation of Shannon and R\´enyi entropies of unknown discrete distributions is a fundamental problem in statistical property testing and an active research topic in both theoretical computer science and information theory. Tight bounds on the number of samples to estimate these entropies have been established in the classical setting, while little is known about their quantum counterparts. In this paper, we give the first quantum algorithms for estimating α- R\´enyi entropies (Shannon entropy being 1-Renyi entropy). In particular, we demonstrate a quadratic quantum speedup for Shannon entropy estimation and a generic quantum speedup for α-R\´enyi entropy estimation for all α \≥ 0, including a tight bound for the collision-entropy (2-R\´enyi entropy). We also provide quantum upper bounds for extreme cases such as the Hartley entropy (i.e., the logarithm of the support size of a distribution, corresponding to α = 0) and the min-entropy case (i.e., α = +\∞), as well as the Kullback-Leibler divergence between two distributions. Moreover, we complement our results with quantum lower bounds on α-R\´enyi entropy estimation for all α \≥ 0. Our approach is inspired by the pioneering work of Bravyi, Harrow, and Hassidim (BHH) [13] on quantum algorithms for distributional property testing, however, with many new technical ingredients. For Shannon entropy and 0-R\´enyi entropy estimation, we improve the performance of the BHH framework, especially its error dependence, using Montanaro\’s approach to estimating the expected output value of a quantum subroutine with bounded variance [41] and giving a fine-tuned error analysis. For general α-R\´enyi entropy estimation, we further develop a procedure that recursively approximates α-R\´enyi entropy for a sequence of αs, which is in spirit similar to a cooling schedule in simulated annealing. For special cases such as integer α \≥ 2 and α = +\∞ (i.e., the min-entropy), we reduce the entropy estimation problem to the α-distinctness and the dlog ne-distinctness problems, respectively. We exploit various techniques to obtain our lower bounds for different ranges of α, including reductions to (variants of) existing lower bounds in quantum query complexity as well as the polynomial method inspired by the celebrated quantum lower bound for the collision problem.

}, url = {https://arxiv.org/abs/1710.06025}, author = {Tongyang Li and Xiaodi Wu} }